This project will develop a quicker and more efficient way to assess people with memory concerns. Our solution is a conversational tool (CognoSpeak:tm:) that asks questions using a ‘talking head’ on a laptop, tablet or smartphone and carefully analyses the spoken answers to detect early signs of dementia. Funded by NIHR i4i; £1.3M; 2022-2025
This project aims to modify out CognoSpeak tool for the stroke survivors. It will provide an easy-to-use, home-based method for monitoring cognitive health post stroke by automatically analysing a person’s speech and language as they speak with an on-screen virtual agent. Funded by Rosetrees Trust Interdisciplinary 2019 Prize for Medicine & AI; £250,000; 2020-2023
Piloting development of an automated approach to coding expressed emotion in mothers’ speech to improve prediction of youth mental health problemsImproving diagnosticprocedures for epilepsythrough automatedrecording and analysisof patient’s history; Funded by the PSYCHIATRY RESEARCH TRUST, 2021-2022.
What are the prevailing EDI issues in current speech technologies and how do we successfully mitigate the resulting biases?; Funded by Research England, 2022.
Creating more intelligent, context-aware communication aids for people with natural but disordered speech; Funded by Research England, 2022.
Improving diagnosticprocedures for epilepsythrough automatedrecording and analysisof patient’s history; Funded by the Epilepsy Research UK, 2019-2022.
This project aims to modify out CognoSpeak tool for the stroke survivors. It will provide an easy-to-use, home-based method for monitoring cognitive health post stroke by automatically analysing a person’s speech and language as they speak with an on-screen virtual agent. Funded by Rosetrees Trust Interdisciplinary 2019 Prize for Medicine & AI; £250,000; 2020-2023
Co-design and initialevaluation of anavatar-basedconversationintervention prototype
Cloud-based Clinical Applications of Speech Technology
CloudVent will provide a cloud-based speech recognition technology for people with Spinal Cord Injury.
This project developed and evaluated a system for automatic assessment of a person’s cognitive impairment based on how they interact with an on-screen digital doctor virtual agent.
This project began the implementation of a more responsive and user-friendly CognoSpeak interface.
This project aims to create an easy-to-use cognitive assessment tool specifically designed for the needs of stroke survivors. It will be based on our stratification tool COCOA (COmputational COgnitive Assessment), developed for detecting early signs of dementia. The tool uses automatic analysis of conversations that patients have with an on-screen digital doctor. The patients’ speech is and analysed for signs of cognitive decline using speech recognition and machine learning classification. . Funded by the FAST Healthcare NetworksPlus Project. 2019
DeepArt:Deep learning for articulatory-based disordered speech recognition
Developing an Artificial Intelligence Empathy Agent
homeService involved a longitudinal study of physically impaired people with dysarthria using voice-enabled assistive technology to control electronic devices in their home.
Remote monitoring people with Mild Cognitive Impairment using combined technology of the Digital Doctor and ViVA; This project will investigate whether OTs can assess PwMCI in their own home using CognoSpeak in combination with the ViVA remote visit system. PwMCI would use their own smartphone or tablet (facilitated by support worker or family member) or have one provided. Funded by Health & Care Partnership
This project aimed to investigate the developing non invasive tools that utilize speech analysis and QEEG to measure cognitive function in resource poor settings. Funded by the University of Sheffield GRCF pump priming award; 2019
Technology Assisted Recovery Goal Elicitation and Transaction (TARGET)– Preparatory wor